language: en datasets: - huggingartists/ghost tags: - huggingartists - lyrics - lm-head - causal-lm widget: - text: I am
I was made with huggingartists.
Create your own bot based on your favorite artist with the demo!
How does it work?
To understand how the model was developed, check the W&B report.
The model was trained on lyrics from Ghost.
Dataset is available here. And can be used with:
from datasets import load_dataset dataset = load_dataset("huggingartists/ghost")
Explore the data, which is tracked with W&B artifacts at every step of the pipeline.
The model is based on a pre-trained GPT-2 which is fine-tuned on Ghost's lyrics.
Hyperparameters and metrics are recorded in the W&B training run for full transparency and reproducibility.
At the end of training, the final model is logged and versioned.
How to use
You can use this model directly with a pipeline for text generation:
from transformers import pipeline generator = pipeline('text-generation', model='huggingartists/ghost') generator("I am", num_return_sequences=5)
Or with Transformers library:
from transformers import AutoTokenizer, AutoModelWithLMHead tokenizer = AutoTokenizer.from_pretrained("huggingartists/ghost") model = AutoModelWithLMHead.from_pretrained("huggingartists/ghost")
Limitations and bias
The model suffers from the same limitations and bias as GPT-2.
In addition, the data present in the user's tweets further affects the text generated by the model.
Built by Aleksey Korshuk
For more details, visit the project repository.